paper-with-me

홈 › Papers

Exploring Sparsity for Parameter Efficient Fine Tuning Using Wavelets

2025-05-18 · Ahmet Bilican, M. Akin Yilmaz, A. Murat Tekalp, R. Gökberk Cinbiş

Efficiently adapting large foundation models is critical, especially with tight compute and memory budgets. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA offer limited granularity and effectiveness in few-parameter regimes. We propose Wavelet Fine-Tuning (WaveFT), a novel PEFT method that learns highly sparse updates in the wavelet domain of residual matrices. WaveFT allows precise control of trainable parameters, offering fine-grained capacity adjustment and excelling with remarkably low parameter count, potentially far fewer than LoRA's minimum, ideal for extreme parameter-efficient scenarios. Evaluated on personalized text-to-image generation using Stable Diffusion XL as baseline, WaveFT significantly outperforms LoRA and other PEFT methods, especially at low parameter counts; achieving superior subject fidelity, prompt alignment, and image diversity.

📄 PDF Abstract BibTeX arXiv:2505.12532

Code (1)

bilican/sparse_peft 공식 구현 pytorch

Tasks

DiversityImage Generationparameter-efficient fine-tuningText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Graph Neural Networks With Lifting-based Adaptive Graph Wavelets

2021-08-03 · Mingxing Xu, Wenrui Dai, Chenglin Li, Junni Zou 외

Spectral-based graph neural networks (SGNNs) have been attracting increasing attention in graph representation learning. However, existing SGNNs are limited in implementing graph filters with rigid transforms (e.g., grap…

Graph Representation LearningRepresentation Learning

Long Exposure: Accelerating Parameter-Efficient Fine-Tuning for LLMs under Shadowy Sparsity

2025-10-12 · Tuowei Wang, Kun Li, Zixu Hao, Donglin Bai 외 arxiv

The adaptation of pre-trained large language models (LLMs) to diverse downstream tasks via fine-tuning is critical for numerous applications. However, the inefficiency of parameter-efficient fine-tuning (PEFT) techniques…

parameter-efficient fine-tuning

Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets

2026-05-10 · Jens Egholm Pedersen, Tony Lindeberg, Peter Gerstoft arxiv

Spike-based encodings are sparse and energy-efficient, but have largely been formulated probabilistically, disconnected from most signal processing literature. We recast spike encoders as time-causal wavelet frames with …

Wavelets on Graphs via Deep Learning

2013-12-01 · NeurIPS 2013 12 · Raif Rustamov, Leonidas J. Guibas

An increasing number of applications require processing of signals defined on weighted graphs. While wavelets provide a flexible tool for signal processing in the classical setting of regular domains, the existing graph …

Deep Learning

ICP: Immediate Compensation Pruning for Mid-to-high Sparsity

2025-01-01 · CVPR 2025 1 · Xin Luo, Xueming Fu, Zihang Jiang, S. Kevin Zhou

The increasing adoption of large-scale models under 7 billion parameters in both language and vision domains enables inference tasks on a single consumer-grade GPU but makes fine-tuning models of this scale, especial…

GPU